Open-source alternatives to Infinity

LightLLM is a high-performance serving framework for deploying and executing large language models. It functions as a multi-GPU inference engine and server capable of handling dense architectures, mixture-of-experts designs, and multimodal models that process both text and images. The system is distinguished by its specialized support for Mixture-of-Experts models using expert parallelism and fused kernels. It implements structured text generation through deterministic state machines and pushdown automata to enforce precise output formats. To optimize throughput, the framework employs specula

TensorRT-LLM is a platform and toolkit designed for compiling, optimizing, and serving transformer-based models on accelerated hardware. It functions as a framework that transforms machine learning models into efficient execution graphs, providing an engine to refine these models for specific hardware to maximize throughput and minimize latency during text generation. The project distinguishes itself through advanced execution strategies that manage the entire inference pipeline. It utilizes kernel-level fusion and static graph execution to optimize mathematical operations and computational f

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

Open WebUI is a self-hosted, web-based platform designed for interacting with local and remote artificial intelligence models. It functions as a unified interface and orchestration suite, enabling users to build, deploy, and manage specialized AI agents equipped with custom instructions, external tool access, and private knowledge bases. The platform distinguishes itself through a modular architecture that supports complex AI workflows. It features a plugin-based framework for custom logic and pipeline-based request processing, allowing developers to filter or transform data streams before th

lmdeploy is a high-performance inference engine and deployment framework for large language models and vision models. It functions as a multi-modal model server and compression toolkit designed to serve models with high throughput and low latency. The system enables the distribution of model services across multiple machines using request-based load balancing and tensor parallelism. It includes specialized tools for model quantization and compression to reduce the memory footprint of weights and caches. The framework covers broad capability areas including production deployment, distributed

Airllm is a framework designed to execute and fine-tune large language models on consumer-grade hardware. By employing layer-wise model decomposition and memory-efficient loading techniques, the engine enables the operation of massive models that would otherwise exceed available system or video memory. The project distinguishes itself through a suite of optimization strategies that balance memory footprint with performance. It utilizes block-wise weight quantization and asynchronous layer prefetching to reduce resource consumption and hide data transfer latency. Additionally, the framework su

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Flowise is a low-code platform designed for building and deploying complex language model workflows through a visual, node-based interface. It functions as an orchestrator for autonomous multi-agent systems, allowing users to construct conversational pipelines by connecting language models, memory stores, and external tools on a drag-and-drop canvas. The platform distinguishes itself through its support for sophisticated agentic patterns, including supervisor-worker delegation and iterative reasoning strategies. Users can design directed acyclic graphs to manage conditional branching, state p

SkyPilot is a multi-cloud AI orchestrator and distributed task scheduler designed to launch and manage AI workloads across various cloud providers, Kubernetes, and Slurm clusters. It functions as an infrastructure-as-code framework that uses declarative files to define resource requirements and setup commands for consistent execution across different environments. The project differentiates itself through automated cost optimization, selecting the most affordable GPU or TPU hardware and managing spot instances to reduce expenses. It also provides a remote development environment that bridges

llama.cpp is a high-performance C++ inference engine and runtime for executing large language models locally across various hardware architectures. It provides the core components for local model execution, including a dedicated model quantizer for compressing weights into the GGUF format and a system for generating text embeddings for semantic search. The project distinguishes itself through specialized memory and execution optimizations, such as block-wise weight quantization to reduce memory footprints and memory-mapped model loading. It supports structured text generation by using formal

Shimmy is a local large language model inference engine and server that loads and serves GGUF formatted weights. It is distributed as a single binary runtime written in Rust, providing a standalone environment for running models without external runtime dependencies. The project utilizes WebGPU for hardware acceleration, allowing model compute kernels to execute across diverse graphics hardware through a standardized interface. It features a local server that implements an OpenAI-compatible API layer, enabling applications to interface with local models via standardized REST endpoints. Memor

Ktransformers is a comprehensive framework designed for the operation, fine-tuning, and serving of large language models. It functions as a heterogeneous inference engine and quantized execution runtime, enabling the deployment of massive models by distributing computational workloads across both CPU and GPU resources. This architecture allows users to bypass local memory constraints, making it possible to run and train models that exceed the capacity of a single device. The project distinguishes itself through specialized support for sparse architectures, particularly mixture-of-experts mode

Llama.cpp is an inference engine designed for the local execution of text-based and multimodal language models on consumer hardware. It provides a core environment for running models that process both text and image inputs, utilizing hardware-accelerated backends to optimize performance across diverse CPU and GPU architectures. The project distinguishes itself by offering a lightweight HTTP server that adheres to standard API specifications, enabling chat completion, embeddings, and reranking services. It includes a suite of tools for model quantization and conversion, which reduces memory us

Text Embeddings Inference is a high-performance inference server designed to host text embedding and sequence classification models as scalable API endpoints. It provides a vector embedding API to convert text into dense representations and a cross-encoder reranking server for scoring the relevance of document sequences against a query. The project features a GPU-accelerated inference engine that utilizes dynamic batching and specialized kernels to maximize throughput. It offers a high-performance binary interface via gRPC as an alternative to standard HTTP to reduce network latency and seria

Text Generation Inference is a production-ready engine designed for the deployment and serving of large language models. It functions as a containerized runtime environment that manages model execution, scales across distributed hardware, and provides high-performance inference capabilities for demanding production environments. The project distinguishes itself through advanced optimization techniques, including continuous batching to maximize hardware utilization and tensor parallelism to shard large models across multiple accelerator cards. It supports efficient inference through custom com

OpenLLM is a framework for deploying, managing, and scaling open-source large language models

LitServe is a Python AI inference server framework and LLM serving framework designed for high-concurrency inference. It functions as a distributed AI model server and dynamic batching inference engine, providing the tools to build and host custom servers that run AI models. The framework distinguishes itself through a dynamic-batching request queue that groups individual inference requests into single tensors to maximize GPU throughput. It supports distributed GPU scaling, allowing model workloads to be spread across multiple hardware accelerators to balance compute loads and increase total

LARK is a development toolkit for training, fine-tuning, and deploying large language models and multimodal models based on PaddlePaddle. It functions as a comprehensive framework that includes an LLM training orchestrator, an inference server, and a multimodal model framework for processing text, image, and video inputs. The project features a retrieval-augmented generation system for building conversational applications that integrate web search and private knowledge bases. It provides specific capabilities for multimodal reasoning and complex logic, enabling the extraction of structured da

This is a collection of Jupyter notebooks that serve as educational guides for training, fine-tuning, and deploying machine learning models within the Hugging Face ecosystem. The notebooks cover the full lifecycle of model development, from loading and configuring pre-trained transformers to packaging trained models for real-time inference via scalable endpoints. The notebooks demonstrate a range of capabilities including diffusion model training and fine-tuning for image generation and editing, transformer model adaptation for natural language processing tasks, and parameter-efficient fine-t

The PyTorch Tutorials repository is a collection of educational resources that provides step-by-step guidance on building, training, and deploying neural networks using the PyTorch framework. It covers the complete machine learning workflow, from data loading and model definition through optimization loops and model persistence, with dedicated guides for distributed training, model fine-tuning, and deployment. The tutorials offer practical demonstrations of adapting pre-trained models to new tasks through transfer learning, scaling training across multiple GPUs or machines using PyTorch's dis

AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc

OptiLLM is an inference proxy and gateway router that directs prompts to specific language models based on cost, performance, and provider health. It functions as a middleware layer designed to optimize requests through intelligent routing, load balancing, and context management. The project provides specialized capabilities for data protection by anonymizing personally identifiable information before requests reach a model. It also acts as a reasoning orchestrator and tool integration layer, using inference-time loops and self-reflection to improve accuracy while connecting models to externa

Nano-vllm is a high-performance inference engine designed for executing large language models locally. It functions as a specialized runtime that prioritizes accelerated token generation and efficient hardware utilization for text generation tasks. The project distinguishes itself through a comprehensive suite of optimization techniques, including a graph compilation engine that transforms neural network operations into pre-compiled execution plans. It also incorporates a tensor parallelism framework to distribute model weights across multiple hardware accelerators, effectively reducing memor

Python package for LLM compression

Cherry Studio is a cross-platform desktop application that serves as a centralized workspace for managing and interacting with multiple artificial intelligence models. It functions as a local-first orchestrator, prioritizing user privacy by storing all conversation history and knowledge bases directly on your device. By providing a unified interface for both cloud-based and local AI services, the platform simplifies API key management and allows for consistent model interaction across different operating systems. The application distinguishes itself through a robust retrieval-augmented genera

Enchanted is a privacy-focused, cross-platform chat frontend for interacting with self-hosted large language models on iOS and macOS. It serves as a native client for communicating with private model servers, specifically providing integration for the Ollama API. The application supports multimodal interactions, allowing users to combine text, image attachments, and voice prompts. It provides tools for local AI model management, including the ability to define persistent system prompts and switch between different models for specific tasks. The interface includes capabilities for rendering m

FlexGen is an inference engine for large language models designed for high-throughput execution on single or multiple GPUs. It functions as a framework for managing model execution through a combination of memory offloading, weight compression, and pipeline orchestration. The system enables the execution of models that exceed available GPU memory by moving tensors and caches between GPU memory, system RAM, and disk storage. It utilizes 4-bit weight quantization to reduce the memory footprint of model parameters, allowing for increased batch processing capacity. The project covers distributed